Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/stayce/icf-mcp-server/claude-mdgit clone --depth 1 https://github.com/stayce/icf-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/stayce/icf-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/stayce/icf-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/stayce/icf-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02417 | $0.02417 |
| Opus 5 | $0.01208 | $0.01208 |
| Sonnet 5 | $0.00483 | $0.00483 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
icf-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
ICF MCP Server (icf-mcp-server v0.1.0) is a Model Context Protocol (MCP) server that provides tools for accessing the WHO International Classification of Functioning, Disability and Health (ICF) classification system via the WHO ICD-API. It enables AI assistants (e.g., Claude) to look up, search, and browse ICF codes through a standardized tool interface.
Repository: stayce/icf-mcp-server (MIT License)
Architecture
Package Layout
src/icf_mcp/
├── __init__.py # Package exports: main, mcp, WHOICFClient, ICFEntity, ICFSearchResult
├── instruments.py # Clinical assessment instruments with ICF mappings (971 lines)
├── server.py # FastMCP server with 17 MCP tools + qualifier parsing (1400 lines)
└── who_client.py # Async WHO ICD-API client with OAuth2 auth (509 lines)
Uses src/ layout with Hatchling build system. Entry point: icf-mcp = "icf_mcp:main".
Three-Module Design
server.py— FastMCP server defining 17 tools via@mcp.tool()decorators:icf_lookup(code)— Look up a specific ICF code (e.g., "b280", "d450")icf_search(query, max_results=10)— Search by keywordsicf_browse_category(category)— Browse categories and sub-chapters ("b", "d4", "e3", etc.)icf_get_children(code)— Get subcategories of a codeicf_explain_qualifier(component, qualifier)— Component-specific qualifier reference (b/s/d/e)icf_overview()— Return full ICF classification overviewicf_get_parent(code)— Navigate up the hierarchy to a code's parent categoryicf_get_siblings(code)— Get codes at the same level (same parent)icf_validate_code(code)— Validate code format, qualifiers, and verify existenceicf_parse_qualified_code(code)— Parse fully qualified codes (d450.23, s730.312, e120+3)icf_build_profile(codes)— Build a structured functional profile from multiple codesicf_get_code_chain(code)— Show the full hierarchy path from root to a codeicf_list_instruments(domain)— List available clinical assessment instrumentsicf_instrument_details(name)— Full instrument spec: items, scoring, ICF mappingsicf_score_instrument(name, responses)— Score responses and get clinical interpretationicf_suggest_instruments(condition, icf_code, domain)— Suggest instruments for a condition or ICF codeicf_instrument_icf_mapping(name)— Show how an instrument maps to ICF codes
instruments.py— Clinical assessment instrument definitions with ICF mappings. 11 instruments: GAD-7, PHQ-9, RADAI-5, SLEDAI-2K, WHODAS 2.0, HAQ-DI, PROMIS-10, CAT, ODI, NRS Pain, Short FES-I. Includes scoring logic, score interpretation ranges, and alias resolution.who_client.py—WHOICFClientclass handling OAuth2 client credentials auth and all HTTP communication with the WHO ICD-API
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 197 lines · 2,417 tokens per session scan A 225054cb6c39
icf-mcp-server CLAUDE.md is an instructions file published in the GitHub repository stayce/icf-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 2,417 tokens to every session, about $0.0121 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
HealthChain CLAUDE.md
Claude Code instructions for healthchainai/HealthChain, covering healthchain - claude code context, 0. project overview, 1. non-negotiable golden rules, 2. testing discipline and 3. build, test & utility commands.
medical-terminologies-mcp CLAUDE.md
Claude Code instructions for SidneyBissoli/medical-terminologies-mcp, covering claude.md, commands, runtime requirements, architecture and two entry points, one registration module (sdk v2).
HealthClawGuardrails GEMINI.md
Gemini CLI instructions for aks129/HealthClawGuardrails, covering healthclaw guardrails — gemini extension context, what the tools do and how to behave.
healthcareskills AGENTS.md
AGENTS.md instructions for aks-builds/healthcareskills, covering agents.md, repository overview, repository structure, agent skills specification and required frontmatter.
rootcause-mcp copilot-instructions.md
Copilot instructions for u9401066/rootcause-mcp, covering copilot 自定義指令, 專案概述, 開發哲學 💡, 法規層級 and 架構原則.
mchs AGENTS.md
AGENTS.md instructions for edithatogo/mchs, a project described as: Software tools for IHACPA National Weighted Activity Unit microcosting and health-service funding calculations.